mirror of
https://github.com/deepseek-ai/DeepInfer.git
synced 2026-10-29 07:17:08 +08:00
- Engram: gather rows where the table lives (host by default, read via UVA on GPU) and move them to the compute device. - EPHandle: the topk_idx version guard tolerates inference-mode tensors on the neuron device that do not report is_inference(). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| vendor | ||
| __init__.py | ||
| NEURON_PORT.md | ||
| transfer_to_neuron.py | ||